© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. Residual Stream
    9. 7-RESID
    11. 1295
    Prev
    Next
    INDEX
    Explanations

    casting string to type (negative activations)

    python-code · gemini-2.5-flash-lite

    url.parse or urllib.parse

    python-code · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 256 tokens each
    Dataset (Dashboard)
    neuronpedia/python-code-simplified
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     set
    -0.09
     values
    -0.09
    _path
    -0.08
     de
    -0.07
     l
    -0.07
     output
    -0.07
    _cost
    -0.03
    D
    -0.03
    '
    0.00
    #
    0.00
    POSITIVE LOGITS
     Get
    0.26
     cur
    0.25
     current
    0.22
     curr
    0.21
    current
    0.21
     _
    0.16
     j
    0.13
     u
    0.12
     i
    0.12
     pi
    0.11
    Activations Density 99.998%

    No Known Activations